{"id":"https://openalex.org/W7220850044","doi":"https://doi.org/10.51775/2790-0886_2026_74_3_139","title":"APPLICATION-LEVEL PERFORMANCE EVALUATION OF A MID-SCALE HPC SYSTEM FOR AI WORKLOADS","display_name":"APPLICATION-LEVEL PERFORMANCE EVALUATION OF A MID-SCALE HPC SYSTEM FOR AI WORKLOADS","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7220850044","doi":"https://doi.org/10.51775/2790-0886_2026_74_3_139"},"language":"ru","primary_location":{"id":"doi:10.51775/2790-0886_2026_74_3_139","doi":"https://doi.org/10.51775/2790-0886_2026_74_3_139","is_oa":false,"landing_page_url":"https://doi.org/10.51775/2790-0886_2026_74_3_139","pdf_url":null,"source":{"id":"https://openalex.org/S4387281709","display_name":"\u0412\u0435\u0441\u0442\u043d\u0438\u043a \u0410\u043b\u043c\u0430\u0442\u0438\u043d\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u0438 \u0438 \u0441\u0432\u044f\u0437\u0438","issn_l":"2790-0886","issn":["2790-0886","2790-0894"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I247491477","host_organization_name":"Almaty University of Power Engineering and Telecommunications","host_organization_lineage":["https://openalex.org/I247491477"],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"\u0412\u0435\u0441\u0442\u043d\u0438\u043a \u0410\u043b\u043c\u0430\u0442\u0438\u043d\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u0438 \u0438 \u0441\u0432\u044f\u0437\u0438","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021034112","display_name":"Amirkhan A. Temirbayev","orcid":"https://orcid.org/0000-0001-6759-2774","observed_orcids":["https://orcid.org/0000-0001-6759-2774"]},"institutions":[{"id":"https://openalex.org/I185571130","display_name":"Al-Farabi Kazakh National University","ror":"https://ror.org/03q0vrn42","country_code":"KZ","type":"education","lineage":["https://openalex.org/I185571130"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"A.A. Temirbayev","raw_affiliation_strings":["Farabi Supercomputer Center, Al-Farabi Kazakh National University, Almaty, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0001-6759-2774","affiliations":[{"raw_affiliation_string":"Farabi Supercomputer Center, Al-Farabi Kazakh National University, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157839414","display_name":"Azati Yakufujiang","orcid":"https://orcid.org/0000-0002-3962-5636","observed_orcids":["https://orcid.org/0000-0002-3962-5636"]},"institutions":[{"id":"https://openalex.org/I185571130","display_name":"Al-Farabi Kazakh National University","ror":"https://ror.org/03q0vrn42","country_code":"KZ","type":"education","lineage":["https://openalex.org/I185571130"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Azati Yakufujiang","raw_affiliation_strings":["Farabi Supercomputer Center, Al-Farabi Kazakh National University, Almaty, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-3962-5636","affiliations":[{"raw_affiliation_string":"Farabi Supercomputer Center, Al-Farabi Kazakh National University, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185571130"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75623188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"74","first_page":"139","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.0035000001080334187,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.002400000113993883,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-workloads","display_name":"AI workloads","score":0.7990000247955322},{"id":"https://openalex.org/keywords/large-language-model-inference","display_name":"large language model inference","score":0.890999972820282},{"id":"https://openalex.org/keywords/embedding-generation","display_name":"embedding generation","score":0.8100000023841858},{"id":"https://openalex.org/keywords/mixed-precision","display_name":"mixed precision","score":0.7639999985694885},{"id":"https://openalex.org/keywords/quantization","display_name":"quantization","score":0.9449999928474426},{"id":"https://openalex.org/keywords/inference-latency","display_name":"inference latency","score":0.6759999990463257},{"id":"https://openalex.org/keywords/time-to-first-token","display_name":"time-to-first-token","score":0.7059999704360962},{"id":"https://openalex.org/keywords/multilingual-models","display_name":"multilingual models","score":0.6449999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431000113487244},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6425999999046326},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6123999953269958},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3637000024318695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3580000102519989},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.33489999175071716},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.33379998803138733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C178059732","wikidata":"https://www.wikidata.org/wiki/Q1982529","display_name":"Software performance testing","level":5,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.51775/2790-0886_2026_74_3_139","doi":"https://doi.org/10.51775/2790-0886_2026_74_3_139","is_oa":false,"landing_page_url":"https://doi.org/10.51775/2790-0886_2026_74_3_139","pdf_url":null,"source":{"id":"https://openalex.org/S4387281709","display_name":"\u0412\u0435\u0441\u0442\u043d\u0438\u043a \u0410\u043b\u043c\u0430\u0442\u0438\u043d\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u0438 \u0438 \u0441\u0432\u044f\u0437\u0438","issn_l":"2790-0886","issn":["2790-0886","2790-0894"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I247491477","host_organization_name":"Almaty University of Power Engineering and Telecommunications","host_organization_lineage":["https://openalex.org/I247491477"],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"\u0412\u0435\u0441\u0442\u043d\u0438\u043a \u0410\u043b\u043c\u0430\u0442\u0438\u043d\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u0438 \u0438 \u0441\u0432\u044f\u0437\u0438","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128490261","https://openalex.org/W7138844257","https://openalex.org/W3161014634","https://openalex.org/W4401017948","https://openalex.org/W4404590647","https://openalex.org/W4399398146","https://openalex.org/W3207603082","https://openalex.org/W6891945742","https://openalex.org/W7203553107","https://openalex.org/W4387559231"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"application-level":[4],"performance":[5,32],"evaluation":[6,107],"of":[7,87,102,108],"a":[8,139],"mid-scale":[9,133],"high-performance":[10],"computing":[11],"(HPC)":[12],"system,":[13],"focusing":[14],"on":[15,25,121],"real-world":[16],"AI":[17,55,145],"workloads.":[18,43],"Unlike":[19],"traditional":[20],"benchmarking":[21],"studies":[22],"that":[23,47,113,132],"focus":[24],"hardware":[26],"characteristics,":[27],"this":[28,103],"work":[29,104],"evaluates":[30],"practical":[31,127],"using":[33],"large":[34,118],"language":[35,110],"model":[36],"(LLM)":[37],"inference,":[38,66],"embedding":[39,74],"generation,":[40],"and":[41,72,95,130,143],"CUDA-based":[42],"The":[44,81,124],"study":[45],"demonstrates":[46],"mid-range":[48],"GPU":[49],"infrastructure":[50],"can":[51,136],"effectively":[52],"support":[53],"modern":[54],"applications,":[56],"achieving":[57],"up":[58],"to":[59],"39.6":[60],"tokens":[61],"per":[62,79],"second":[63],"for":[64,141],"LLM":[65],"low":[67],"latency":[68],"(25-31":[69],"ms":[70],"time-to-first-token),":[71],"high":[73],"throughput":[75],"exceeding":[76],"56,000":[77],"sentences":[78],"second.":[80],"results":[82],"further":[83],"highlight":[84],"the":[85,106],"importance":[86],"software":[88],"optimization":[89],"techniques,":[90],"including":[91],"mixed":[92],"precision,":[93],"quantization,":[94],"optimized":[96],"inference":[97],"frameworks.":[98],"A":[99],"key":[100],"contribution":[101],"is":[105],"Kazakh":[109],"models,":[111],"showing":[112],"language-specific":[114],"models":[115,120],"significantly":[116],"outperform":[117],"multilingual":[119],"domain-specific":[122],"tasks.":[123],"findings":[125],"provide":[126],"deployment":[128],"guidelines":[129],"demonstrate":[131],"HPC":[134],"systems":[135],"serve":[137],"as":[138],"foundation":[140],"scalable":[142],"cost-effective":[144],"infrastructure.":[146]},"counts_by_year":[],"updated_date":"2026-10-09T09:14:12.587421","created_date":"2026-10-08T00:00:00"}